Skip to content
Navigation Menu
Sign in
Products
Platform
GitHub
Repository hosting, code review, and collaboration
Copilot
AI coding agent for tasks, projects and automated work
Build & Ship
Actions
CI/CD and automation
Code Quality
Quality analysis, fixes, and enforcement
Codespaces
Cloud development environments
Secure
Code Security
Vulnerability detection and remediation
Secret Protection
Secret scanning and leak prevention
All Features
Developers
Learn
Documentation
Training
Certifications
Build
Build with Copilot
Customize Copilot
Integrations
Explore
Trending repos
GitHub Sponsors
Events
Changelog
Changelog
Your source for the latest features, improvements, and fixes across GitHub products, all in one place.
Businesses
By Stage
Enterprises
Team
Startups
Nonprofits
By Industry
Healthcare
Financial services
Manufacturing
Government
See all industries
Evaluate GitHub
Why GitHub
Customer Stories
Business insights
Trust Center
Add-ons
GitHub Advanced Security
Enterprise-grade code security
Copilot for business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Resources
Learn & Connect
Documentation
Resource center
Blog
Events & webinars
Community Forum
Customer Stories
Integrations
Support
Customer support
Training
GitHub Status
Company
About
Partners
Changelog
GitHub Universe
GitHub Universe
The event for developers, by developers — talks, workshops, and what’s next for GitHub.
Pricing
Search
/
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
NVIDIA
Model-Optimizer
Repository navigation
Code
Issues
95
(95)
Pull requests
437
(437)
Actions
Security and quality
Insights
More
items
docs(qwen3.6): isolation/loss-mask rerun, chat-SFT kernel correction, Omniscience calibration, announcement update
- #2899
#2899
Merged
kevalmorabia97
merged 8 commits into
main
NVIDIA/Model-Optimizer:main
from
kmorabia/qwen36-tutorial-isolation
NVIDIA/Model-Optimizer:kmorabia/qwen36-tutorial-isolation
Copy head branch name to clipboard
Oct 26, 2026
Conversation
Commits
8
(8)
Checks
Files changed
Merged
docs(qwen3.6): isolation/loss-mask rerun, chat-SFT kernel correction, Omniscience calibration, announcement update
#2899
kevalmorabia97
merged 8 commits into
main
NVIDIA/Model-Optimizer:main
from
kmorabia/qwen36-tutorial-isolation
NVIDIA/Model-Optimizer:kmorabia/qwen36-tutorial-isolation
Copy head branch name to clipboard
Commits
Commits on Oct 21, 2026
docs(qwen3.6): add controlled isolation/loss-mask rerun and correct the chat-SFT caveat
Show description for 80f498c
kevalmorabia97
and
claude
committed
80f498c
View commit details
Copy full SHA for 80f498c
Browse repository at this point
docs(qwen3.6): add AA-Omniscience calibration results and update the announcement
Show description for 577e92f
kevalmorabia97
and
claude
committed
577e92f
View commit details
Copy full SHA for 577e92f
Browse repository at this point
docs(qwen3.6): address review on Omniscience docs
Show description for 6cea36b
kevalmorabia97
and
claude
committed
6cea36b
View commit details
Copy full SHA for 6cea36b
Browse repository at this point
docs(qwen3.6): list fully on-policy KD as the untested QAD option
Show description for 234b045
kevalmorabia97
and
claude
committed
234b045
View commit details
Copy full SHA for 234b045
Browse repository at this point
docs(qwen3.6): arm B never split documents; treat it as a repeat of A
Show description for d6711a8
kevalmorabia97
and
claude
committed
d6711a8
View commit details
Copy full SHA for d6711a8
Browse repository at this point
Commits on Oct 22, 2026
docs(qwen3.6): per-document attention is untested; point the EOS fix at #2912
Show description for 3f02590
kevalmorabia97
and
claude
committed
3f02590
View commit details
Copy full SHA for 3f02590
Browse repository at this point
docs(qwen3.6): address review on Omniscience grades, timeout and ablation lead-in
Show description for f32d623
kevalmorabia97
and
claude
committed
f32d623
View commit details
Copy full SHA for f32d623
Browse repository at this point
Commits on Oct 26, 2026
docs(qwen3.6): reword the Omniscience calibration takeaway
Show description for 80616ff
kevalmorabia97
and
claude
committed
80616ff
View commit details
Copy full SHA for 80616ff
Browse repository at this point
You can’t perform that action at this time.